agent-orchestration

agent-orchestration is a skill for Claude Code, Codex from mrpulor-gh/nuphus. It costs 0 tokens per session (7,921 once invoked), scanned A, original, Apache-2.0.

A guide for coordinating independent AI coding agents such as Claude Code, OpenCode, or Hermes. It explains how to register each agent, check which ones are running, choose one for a task, and record stable information about how to use it.

In plain words
What is it for?
Adding external agents to a team configuration, checking their availability, matching tasks to their interaction mode, dispatching work, and recording a successful setup for later use.
Why use it?
It reduces confusion when several external agents are available with different ways of communicating and starting. It also prevents temporary process details such as process IDs or window handles from being used as permanent configuration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Adding external agents to a team configuration, checking their availability, matching tasks to their interaction mode, dispatching work, and recording a successful setup for later use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mrpulor-gh/nuphus/agent-orchestration
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mrpulor-gh/nuphus --skill agent-orchestration
Clone the repo
git clone --depth 1 https://github.com/mrpulor-gh/nuphus

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/agent-orchestration/github.svg)](https://agentmods.dev/skills/mrpulor-gh/nuphus/agent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/agent-orchestration"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/agent-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/agent-orchestration"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/agent-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,921 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.07921
Opus 5.5 $0.00000 $0.03168
Sonnet 5.5 $0.00000 $0.01584
Haiku 4.5 $0.00000 $0.00792

Measured 11d ago against content hash 2c51d7d6534a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-orchestration scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 终端类:curl 直调;**PowerShell 必须发 UTF-8 字节体**(`-Body ([Text.Encoding]::UTF8.GetBytes($json))`),字符串 body 会把中文压成 `?`(实测);纯 ASCII body 才可用单引号直传
plugin/skills/builtin/agent-orchestration/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 平台编排

外部 Agent(独立终端 TUI / 桌面 App / Web 等平台)协作指南。系统提示词已覆盖的(工具描述/annotation/Constitution)不重复,本技能只写外部 Agent 特有流程。

铁律:非显式指定不派发外部 Agent。


1. 登记(team.toml)

渐进登记:每用一个外部 Agent,在 plugin/team.toml 追加一段。只记稳定事实(mode/launch/process/window_hint/dispatch_steps/note);PID/hwnd 每次启动必变、hwnd 会被 OS 复用给无关窗口——一律按当次实况重新解析,禁止写死。

本段只示格式(键名与注释);字段值一律占位,不代表任何已登记 agent 的实况。 任何具体 agent 的字段值,一律以 plugin/team.toml 当次读取为准。 完整段示例(含 dispatch_steps)见本节末尾第 3 条,此处不重复。

双登记路径(实测均有效):

  • 手改 team.toml:直接编辑保存即可被运行中系统即时读取(无需重启),适合快速实验与本轮临时接入;
  • 配置中心录入:桌面 设置 → 外部 Agent → 新增(走 upsert_external_agent),适合正式归档——会联动生成 handoff 工作目录(read.md/memory.md/status.json),手改路径不生成这些文件(须后续补 agent_init 或由首次 dispatch 补建空骨架)。

调用决策:Read team.toml → process_list 看谁活着(活着优先)→ 按平台能力匹配。不维护历史评分。

跑通即归档(强制,当轮完成)

新外部 Agent 首次跑通验证后,必须当轮登记归档,禁止「以后再用再配」——不归档则下次会话无从知晓其存在与用法,跑通经验直接丢失。

  1. 配置中心录入:桌面 设置 → 外部 Agent → 新增(走 upsert_external_agent):
    • 派发必需:key(唯一、保存后不可改)/ mode(窗口分类依据,§2 交互方式由此决定)/ launch+args(§2 启动 SOP 手动启动用)/ window_hint(终端类标题常被覆写,选稳定前缀)/ process(process_list 识别依赖此字段)/ dispatch_steps(§1.1——配错一步指令就打不进去,第一责任区)
    • 人读与备忘:display_name/icon/description(description 会同步为该 agent read.md 的职责段);note = Leader 专属实测备忘(随配置读取、派发结果回显、UI 禁编辑)——opencode 的「window_hint 扫描无效、走 pid 路径」结论就记在这里

    已废弃不生效:cooldown_secs / await_timeout_secs / timeout_action / timeout_script / auto_approve / auto_approve_script / confirm_keywords——早期设想均未落地,配了等同没配,不要依赖(后端仅为旧配置兼容解析,UI 不再提供录入)。字段全集以代码为准:AgentFields(src-tauri/src/commands/config/team.rs)。

  2. 落盘核对:plugin/team.toml 出现该段且原有段未被破坏(写回是段级增量);新 key 联动生成 handoff 工作目录。
  3. 完整段示例(全量字段的格式示例;值一律占位,实况以 plugin/team.toml 为准):
[{key}]
mode = "embedded"        # background | embedded | standalone | web
display_name = "<显示名>"
icon = "terminal"
launch = "<启动命令>"
window_hint = "<窗口特征>"
process = "<进程名>"
note = "<Leader 实测备忘>(Leader 专属,UI 不可编辑)"

[[{key}.dispatch_steps]]
tool = "desktop_window_activate"
with = { hwnd = "{hwnd}" }

[[{key}.dispatch_steps]]
tool = "__sleep"
with = { ms = 500 }

[[{key}.dispatch_steps]]
tool = "desktop_input"
with = { hwnd = "{hwnd}", mode = "type", text = "{message}", send = "none" }

[[{key}.dispatch_steps]]
tool = "desktop_input"
with = { hwnd = "{hwnd}", mode = "hotkey", keys = ["enter"] }

Read the full file on GitHub · 328 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago Changed · +3 lines 2c51d7d6534a
  2. 24d ago Changed 9fd87805dede
  3. 26d ago Changed 87a8b23af8d1
  4. 27d ago Changed · -32 lines 5d9ce2e25668
  5. 1mo ago Changed · +2 lines 5e5183fc6ba7
  6. 1mo ago Changed · +5 lines a37bac260e59
  7. 1mo ago First seen · 350 lines · 0 tokens per session scan A d7f66500cdf3

Subscribe to this mod's changes

agent-orchestration is a skill published in the GitHub repository mrpulor-gh/nuphus (89 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 7,921 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

tcapi

A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.

TencentCloud/Octop · 68 tokens

macos-harness

Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.

browser-use/macos-harness · 40 tokens

computer-use-linux

Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).

agent-sh/computer-use-linux · 39 tokens

byted-mediakit-voiceover-editing

Volcano Engine AI MediaKit talking-head video editing Skill: a one-stop workflow from environment setup through media management, audio processing, talking-head cuts, video export, review UI, and iterative refinement. You MUST invoke this Skill when the user mentions talking-head editing, cutting talking video, video…

bytedance/agentkit-samples · 104 tokens

desktop-gui-inspect

Full-desktop automation for targets that have no browser and no API at all — a legacy Java-based NMS client, a vendor's Windows-only configuration utility, a terminal emulator with no scriptable interface. Drives OpenClaw's ClawHub computer-use skill (Xvfb+XFCE virtual desktop, xdotool input automation) to read…

automateyournetwork/netclaw · 143 tokens

Market Research Brief

Generate a structured market research brief from a feature idea and supplied business context: market landscape, competitor intelligence, opportunity assessment, and a go-to-market recommendation. Use for market, research, competitor, and product launch requests.

AgentEra/Agently · 48 tokens